.actor

# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:16

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./


# Run the image.
CMD npm start --silent


.actor/Dockerfile

Crawlee and Cheerio project in javascript.

my-actor

Project Cheerio Crawler Javascript

.actor/actor.json

{
            "actorSpecification": 1,
            "views": {
                "overview": {
                    "title": "Overview",
                    "transformation": {
                        "fields": [
  "company_name",
    "universal_name_id",
    "background_cover_image_url",
    "linkedin_internal_id",
    "industry",
    "location",
    "follower_count",
    "tagline",
    "company_size_on_linkedin",
    "about",
    "website",
    "industries",
    "company_size",
    "headquarters",
    "type",
    "founded",
    "specialties",
    "locations",
    "employees",
    "updates",
    "similar_companies",
     "affiliated_companies",
                        ]
                    },
                    "display": {
                        "component": "table",
                        "properties": {
                            "background_cover_image_url": {
                                "label": "background_cover_image_url",
                                "format": "image"
                            }
                        }
                    }
                }
            }
        }

.actor/dataset_schema.json

Linkedin Company pages urls ie.https://www.linkedin.com/company/apifytech

urls

CheerioCrawler Template

.actor/input_schema.json


// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
import { Actor } from 'apify';
// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
import { CheerioCrawler, Dataset } from 'crawlee';

// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
await Actor.init();

// Structure of input is defined in input_schema.json
const {
    urls,
    maxRequestsPerCrawl = 1,
} = await Actor.getInput() ?? {};

const proxyConfiguration = await Actor.createProxyConfiguration();

const crawler = new CheerioCrawler({
    proxyConfiguration,
    maxRequestsPerCrawl,
    async requestHandler({ request, $, log }) {


        log.info(request.loadedUrl);

const content = $('.top-card-layout__first-subline').contents();

    const location = content.first().text().trim();
    const followerCount = content.last().text().trim().split(' ')[0];

    function extractEmployeeCount(html) {
      const regex = /View all (\d{1,3}(?:,\d{3})*) employees/;
      const match = html.match(regex);
      if (match && match[1]) {
        const employeeCount = match[1].replace(/,/g, '');
        return parseInt(employeeCount, 10);
      }
      return 0;
    }
    let company_size_on_linkedin = extractEmployeeCount($('.face-pile__cta').text())


    const locations = [];

    $('section.locations ul.show-more-less__list > li').each((index, element) => {
      const isHQ = $(element).find('span.tag-sm').text().trim() === 'Primary';
      const addressLine1 = $(element).find('div[id^="address-"]').find('p:first-child').text().trim();
      const addressLine2 = $(element).find('div[id^="address-"]').find('p:nth-child(2)').text().trim();
      const locationLink = $(element).find('a.link-no-visited-state').attr('href');

      locations.push({
        is_hq: isHQ,
        office_address_line_1: addressLine1,
        office_address_line_2: addressLine2,
        office_location_link: locationLink,
      });
    });

    let employees = []
    $('section[data-test-id="employees-at"] ul li a.base-card').each((index, element) => {
      const employee = {
        employee_photo: $(element).find('img').attr('data-delayed-url'),
        employee_name: $(element).find('h3.base-main-card__title').text().trim(),
        employee_position: $(element).find('h4.base-main-card__subtitle').text().trim(),
        employee_profile_url: $(element).attr('href')
      };

      employees.push(employee);
    });

    const updates = [];

    $('section[data-test-id="updates"] .updates__list > li').each((index, element) => {
      const text = $(element).find('.attributed-text-segment-list__content').text().trim();
      const articlePostedDate = $(element).find('time').text().trim();
      const totalLikes = $(element).find('[data-test-id="social-actions__reaction-count"]').text().trim();
      const articleImage = $(element).find('[data-test-id="feed-images-content"] img').attr('src');

      updates.push({
        text,
        articlePostedDate,
        totalLikes,
        articleImage
      });
    });

    const similarCompanies = [];

    $('section[data-test-id="similar-pages"] ul.show-more-less__list > li').each((index, element) => {
      const link = $(element).find('a.base-card').attr('href');
      const name = $(element).find('h3.base-aside-card__title').text().trim();
      const summary = $(element).find('p.base-aside-card__subtitle').text().trim();
      const location = $(element).find('p.base-aside-card__second-subtitle').text().trim();

      similarCompanies.push({
        link,
        name,
        summary,
        location,
      });
    });

    const affiliatedCompanies = [];

    $('section[data-test-id="affiliated-pages"] ul.show-more-less__list > li').each((index, element) => {
      const link = $(element).find('a.base-card').attr('href');
      const name = $(element).find('h3.base-aside-card__title').text().trim();
      const industry = $(element).find('p.base-aside-card__subtitle').text().trim();
      const location = $(element).find('p.base-aside-card__second-subtitle').text().trim();

      affiliatedCompanies.push({
        link,
        name,
        industry,
        location,
      });
    });

    let res = {
      company_name: $('.top-card-layout__title').text().trim(),
      universal_name_id : request.loadedUrl.split("/")[4],
      background_cover_image_url: $('.cover-img__image').attr('src'),
      linkedin_internal_id: "",
      profile_photo: $('.top-card-layout__entity-image-container > img').attr('src'),
      industry: $('.top-card-layout__headline').text().trim(),
      location: location,
      follower_count: followerCount.trim(),
      tagline: $('.top-card-layout__second-subline').text().trim(),
      company_size_on_linkedin,
      about: $('.core-section-container__content > p').text().trim(),
      website: $('div[data-test-id="about-us__website"] a').attr('href'),
      industries: $('div[data-test-id="about-us__industries"] > dd').text().trim(),
      company_size: $('div[data-test-id="about-us__size"] > dd').text().trim(),
      headquarters: $('div[data-test-id="about-us__headquarters"] > dd').text().trim(),
      type: $('div[data-test-id="about-us__organizationType"] > dd').text().trim(),
      founded: $('div[data-test-id="about-us__foundedOn"] > dd').text().trim(),
      specialties: $('div[data-test-id="about-us__specialties"] > div').text().trim(),
      locations: locations,
      employees: employees,
      updates: updates,
      similar_companies: similarCompanies,
      affiliated_companies: affiliatedCompanies,
    }


        await Dataset.pushData(res);
    },
});

const cleanUrls = urls.map(item => {
  return {
    url : item.url.split('?')[0]
  }
})

await crawler.run(cleanUrls);

// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
await Actor.exit();


src/main.js

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git


.dockerignore

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf


.editorconfig

{
    "extends": "@apify",
    "root": true
}


.eslintrc

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage


.gitignore

crawlee-cheerio-javascript

package.json

The LinkedIn Company Profile Scraper is a powerful and efficient tool designed to extract valuable information from LinkedIn company profiles with ease. Whether you're a market researcher, sales professional, or just curious about a company's background.

linkedin-company-profile-scraper

Linkedin Company Profile Scraper

Linkedin Company Profile Scraper · Apify

Input · Linkedin Company Profile Scraper · Apify

API · Linkedin Company Profile Scraper · Apify

Related Actors · Linkedin Company Profile Scraper · Apify

The LinkedIn Company Profile Scraper is a powerful and efficient tool designed to extract valuable information from LinkedIn company profiles with ease. Whether you're a market researcher, sales pr...

Where next?